Real people rate your options. You see what's working, , and who it isn't. In about a day.
A brief lands. You make options. Your gut picks the strong ones. Then it goes to the client on instinct. Instinct is usually right about direction. It can't say which part is doing the work, or .
People from your audience look at finished versions of your idea and rate them, one at a time. Each version is built from parts, so can tell what each part added. For everyone, and for each kind of person who looked.
Which part is pulling its weight and which parts are dead. On one sign, six background colours together moved the score by a single point.
Men, women, under 35, over 55. One headline was +13 with men and +2 with women. Same words, different people.
The line that pulls one group in and pushes another away. The small print that gets the business wrong. The clean logo nobody trusts.
A pack scored piece by piece before the client's own shelf test. Purchase intent up 12%. .
The same real people, inside a social feed we control. We watch what they do, not what they say. .
Purchase intent, in the client's own . We scored the pieces, narrowed the field to three, and sent the shortlist in. Every pack on it beat the current product and the competition.
One study, not a hundred. We'll keep showing our work as it grows.
There's no fixed software here. We build the experiment around your asset. When the question needs sensors or a custom build, our technology team builds it. Tell us what you're working on.
Bring a creative, a pack, a logo, or just the brief. Thirty minutes is enough to tell you what a study would look like.
On a farmers-market sign, every headline about values or buying local scored zero with women and six to eight points with men. Women stopped for the discount and the photos of produce.
Age cut the other way. "Organic groceries, fair prices" added seven points with people between 35 and 54 and took ten away with people between 55 and 64.
The overall score said the sign was fine. It was, for some people.
A good gut is right about direction most of the time. What it can't do is split the audience. The headline that feels strongest to you might be the one that only works on people like you.
Test the pieces first and you walk into the room knowing which line to keep, which to cut, and who each one is for.
Each person sees finished versions of your idea, one at a time, and rates each out of five. No questionnaire, no "why".
Every version was put together from parts on purpose, so we know exactly which parts each person saw. From a few hundred ratings, the maths works out how much each part moved the score. Run it on everyone and you get the overall. Run it on just the women, or just the over-55s, and you see who it's working for.
A score of +11 on a headline means it lifts the share of people who'd rate the idea highly by eleven points. Zero means it does nothing. Below zero, it's costing you.
None of this is new. People have been putting feeling on a scale since the 1950s. We made it fast enough for a pitch.
We split a pack into its pieces, tested the variations with shoppers in Brazil and Germany, and scored every combination. A holographic finish added the most. A large-format band helped.
From that we narrowed the field to three packs. The client put the shortlist into its own pre-launch shelf test, against the current product and the competition. All three beat both. Purchase intent went up 12%.
The full study is on request.
Most ads get judged after they're running. We put yours into a social feed we control first, scrolled by real people the way they meet ads. We read attention and intent from what they do, then score the pieces the same way we score a sign.
No ad account, no media spend.